Skip to content

L1 Norm

2 messages · M. Angel Arranz, Brian Ripley

#
Dear R people

I must estimate a linear model with the L1 norm. S-Plus includes the l1fit
command that performs exactly what I need, but I do not know how to do it
in R. I checked the 'lqs' library, but it was not included there. Do you
how to estimate it with R?

Thanks in advance

Miguel A.

************************************
Miguel A. Arranz
Dpt. of Statistics and Econometrics
Universidad Carlos III de Madrid
arranz at pvi.uc3m.es
************************************
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
On Mon, 15 May 2000, M. Angel Arranz wrote:

            
Why?  (Is this a homework?)  There are lots of things wrong with l1 norm
solutions.
Check out the quantreg package on CRAN for a *much* comprehensive solution.
Also, you could use rlm()	 in library MASS with k \approx 0, but k \approx 1
is a much better idea.